© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138115
    Prev
    Next
    INDEX
    Explanations

    places and specific activities

    np_acts-logits-general · gemini-2.5-flash-lite

    Ukrainian objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     त्यांचा
    0.49
     ज्य
    0.49
     разъ
    0.47
    輸入品
    0.46
    лся
    0.46
    ाग्राम
    0.46
    杳
    0.46
    
    0.46
    ѡ
    0.45
     cesse
    0.43
    POSITIVE LOGITS
    പ്പു
    0.51
     constituents
    0.47
    των
    0.47
     ITO
    0.47
     apod
    0.46
     ঘ
    0.46
     roles
    0.45
     Mazz
    0.45
    GROUP
    0.45
    സ്റ്റി
    0.45
    Activations Density 0.000%

    No Known Activations